OSCR

Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools.

Code ↔ Paper

1 match between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 1 match
  1. [1] § Materials and methods › Processing pipeline with different segmentation/surface reconstruction methods ↔ dldirect/radiomics_extractor.py, lines 1–20 · score 0.61 · accumbens, caudate, pallidum, putamen, thalamus, ventral

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 115 lines · 4.4 KB · BSD-3-Clause · 1 match

  1. import argparse
  2. import os
  3. import sys
  4. import pathlib
  5. import radiomics
  6. import SimpleITK as sitk
  7. import csv
  8. import pandas as pd
  11. LABELS_FS = ['Left-Lateral-Ventricle', 'Left-Inf-Lat-Vent', 'Left-Thalamus-Proper', 'Left-Caudate', 'Left-Putamen', 'Left-Pallidum', '3rd-Ventricle',
  12. '4th-Ventricle', 'Brain-Stem', 'Left-Hippocampus', 'Left-Amygdala', 'Left-Accumbens-area', 'Left-VentralDC', 'Left-choroid-plexus',
  13. 'Right-Lateral-Ventricle', 'Right-Inf-Lat-Vent', 'Right-Thalamus-Proper', 'Right-Caudate', 'Right-Putamen', 'Right-Pallidum', 'Right-Hippocampus',
  14. 'Right-Amygdala', 'Right-Accumbens-area', 'Right-VentralDC', 'Right-choroid-plexus', '5th-Ventricle',
  15. 'CC_Posterior', 'CC_Mid_Posterior', 'CC_Central', 'CC_Mid_Anterior', 'CC_Anterior']
  17. LABELS_DL = ['Left-Ventricle-all:101', 'Left-Thalamus-Proper', 'Left-Caudate', 'Left-Putamen', 'Left-Pallidum', 'Left-Hippocampus', 'Left-Amygdala',
  18. 'Left-Accumbens-area', 'Left-VentralDC', 'Right-Ventricle-all:112', 'Right-Thalamus-Proper', 'Right-Caudate', 'Right-Putamen',
  19. 'Right-Pallidum', 'Right-Hippocampus', 'Right-Amygdala', 'Right-Accumbens-area', 'Right-VentralDC', 'Brain-Stem',
  20. '3rd-Ventricle', '4th-Ventricle', 'Corpus-Callosum:125']
  23. def lut_parse():
  24. lut = pd.read_csv('{}/fs_lut.csv'.format(pathlib.Path(__file__).parent.resolve()))
  25. lut = dict(zip(lut.Key, lut.Label))
  26. return lut
  29. def run_main(subject_dirs, aseg_file, labels, results_csv):
  30. LUT = lut_parse()
  31. print(results_csv)
  32. with open(results_csv, 'w') as out_file:
  33. writer = csv.writer(out_file, delimiter=',')
  34. header = None
  35. for subjects_dir in subject_dirs:
  36. for subject_name in sorted(os.listdir(subjects_dir)):
  37. fname = '{}/{}/{}'.format(subjects_dir, subject_name, aseg_file)
  38. if not os.path.exists(fname):
  39. print('{}: {} not found. Skipping'.format(subject_name, aseg_file))
  40. continue
  42. print(subject_name)
  43. fields = list()
  44. values = list()
  45. img = sitk.ReadImage(fname)
  46. for label in labels:
  47. if ':' in label:
  48. label, label_id = label.split(':')
  49. else:
  50. label_id = LUT[label]
  51. radiomics.setVerbosity(50)
  52. shape_features = radiomics.shape.RadiomicsShape(img, img, **{'label': int(label_id)})
  53. shape_features.enableAllFeatures()
  54. results = shape_features.execute()
  55. for key in results.keys():
  56. fields.append('{}.{}'.format(label, key))
  57. values.append(float(results[key]) if results['VoxelVolume'] > 0 else 'nan')
  59. if header is None:
  60. header = fields
  61. writer.writerow(['Subject'] + header)
  62. else:
  63. assert header == fields
  65. writer.writerow([subject_name] + values)
  68. def main():
  69. parser = argparse.ArgumentParser(description='Extract radiomics features from subjects')
  71. parser.add_argument(
  72. '--aseg_file',
  73. type=str,
  74. default='T1w_norm_seg.nii.gz',
  75. help='Path (relative to subject dir) of aseg segmentation file.'
  76. )
  78. parser.add_argument(
  79. '--labels',
  80. type=str,
  81. nargs='+',
  82. metavar='label',
  83. default=['DL'],
  84. help='List of labels. FreeSurfer ids (from fs_lut) are used per default. '
  85. 'Can also be: label:id. Example: "Left-Hippocampus:9 Right-Hippocampus:21." '
  86. 'Use "FS" for all FreeSurfer labels or "DL" for all DL+DiReCT labels'
  87. )
  89. parser.add_argument(
  90. '--results_csv',
  91. type=str,
  92. required=True,
  93. help='CSV-File to store results'
  94. )
  96. parser.add_argument(
  97. 'subject_dirs',
  98. metavar='dir',
  99. type=str,
  100. nargs='+',
  101. help='Directories with subjects (FreeSurfer or DL+DiReCT results dir)'
  102. )
  104. args = parser.parse_args()
  105. for dir in args.subject_dirs:
  106. if not os.path.exists(dir):
  107. print('{} not found'.format(args.dir))
  108. sys.exit(1)
  110. labels = LABELS_FS if args.labels[0] == 'FS' else LABELS_DL if args.labels[0] == 'DL' else args.labels
  111. run_main(args.subject_dirs, args.aseg_file, labels, args.results_csv)
  114. if __name__ == '__main__':
  115. sys.exit(main())

radiomics_extractor.py at commit 0cb3d72, under BSD-3-Clause · at the source

Overview

Authors: Victor B. B. Mello1, Richard McKinley1, Roland Wiest1, Christian Rummel1,2
  1. Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology University of Bern, Inselspital, Bern University Hospital,Bern, Switzerland
  2. European Campus Rottal-Inn, Technische Hochschule Deggendorf,Max-Breiherr-Straße 32, 84347 Pfarrkirchen, Germany
Institutions: University of Bern (Switzerland); Deggendorf Institute of Technology (Germany)
Journal: Scientific reports, volume 16, issue 1, article 20350
Dates: received 28 August 2025; accepted 24 May 2026; published online 12 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41598-026-55397-w · PMID 42286078 · PMCID PMC13328385 · OpenAlex W7164496621
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), human (organism), methods / tools (subfield)
Methods: Statistics, fMRI & imaging, Preprocessing
Keywords: Neuroimaging, Quantitative image analysis, Cortical atrophy, Computational biology and bioinformatics, Engineering, Health care, Mathematics and computing, Medical research
MeSH: Brain*, Deep Learning*, Image Processing, Computer-Assisted*, Magnetic Resonance Imaging*, Adolescent, Adult, Benchmarking, Female, Humans, Male, Middle Aged, Reproducibility of Results, Software, Young Adult (* major topic)
Topic: Advanced Neuroimaging Techniques and Applications (Radiology, Nuclear Medicine and Imaging, Medicine), according to OpenAlex
Funding: SNF (SNF grant 204593); NIH (grant R01NS107513)
Citations: not cited yet (Europe PMC); 63 references in the paper

Abstract

Time efficient and reliable pipelines for quantitative evaluation of structural brain MRI are essential to utilize the potential of morphometry tools for large scale research projects as well as to pave the path towards future clinical applications. In our work, we have explored this idea by evaluating three deep learning models for brain segmentation and cortex parcellation (DeepSCAN, FastSurferCNN and QuickNAT) as input for an 11-min surface reconstruction pipeline adapted from the well studied open source software package FreeSurfer. Performance was assessed using both, large publicly available human MRI datasets and a synthetic dataset with known metrics and reference surfaces. Evaluation criteria included closeness to the surface reconstruction by FreeSurfer’s full recon-all pipeline, reproducibility within same-session rescans, performance stability across a wide age range, sensitivity to variations of the grey-white contrast in the MRI and accuracy regarding metrics of synthetic surfaces. Metrics derived from the DeepSCAN-based pipeline demonstrated the highest agreement with FreeSurfer in the human data and the greatest fidelity to the expected metrics in the synthetic dataset. Our findings identify the DeepSCAN-based surface reconstruction pipeline as a rapid, yet reliable alternative to established research-grade structural MRI processing. Time expenditure and reliability suggest it is suitable for research applications with high-throughput requirements. This is an essential first step towards necessary subsequent studies aimed at evaluating robustness, pathological variability, and utility in the context of clinical diagnostics.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.

SCAN-NRAD/DL-DiReCT-V2

License: BSD-3-Clause
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 0cb3d728b4ef78706e37d12309bc93f12a7c97ef, 22 September 2026
Languages: Python (20), Shell (5)
Size: 46 files, 25 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, license file, environment (pyproject.toml), documentation
Not found: CITATION.cff, tests, continuous integration
Tools: NumPy (16 files), NiBabel (15 files), pandas (9 files), SciPy (7 files), PyTorch (4 files), Nighres (2 files), scikit-image (2 files), scikit-learn (2 files), ANTs (1 file), FreeSurfer (1 file), PyRadiomics (1 file), SimpleITK (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
27 files
At the source: github.com/SCAN-NRAD/DL-DiReCT-V2

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 25 scripts, each with its path and the digest of its content;
  • 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data availability

There is no data release in this paper. All dataset used are public. All scripts necessary to run the fast pipeline reconstruction are available at https://github.com/SCAN-NRAD/DL-DiReCT-V2. The DL-based cortical atrophy phantom generated by Ruskak et al. (2022) was obtained directly from the original authors upon request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 8 keywords, 14 MeSH terms, 2 funders, 53 references.

Cite

This paper

Mello, V. B. B., McKinley, R., Wiest, R., & Rummel, C. (2026). Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools. Scientific reports, 16(1), 20350. https://doi.org/10.1038/s41598-026-55397-w

BibTeX

@article{mello2026fast,
author = {Mello, Victor B. B. and McKinley, Richard and Wiest, Roland and Rummel, Christian},
title = {{Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools}},
journal = {Scientific reports},
year = {2026},
month = jun,
volume = {16},
number = {1},
pages = {20350},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-55397-w},
url = {https://doi.org/10.1038/s41598-026-55397-w},
pmid = {42286078},
pmcid = {PMC13328385}
}

RIS

TY - JOUR
AU - Mello, Victor B. B.
AU - McKinley, Richard
AU - Wiest, Roland
AU - Rummel, Christian
TI - Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/06/12
VL - 16
IS - 1
SP - 20350
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-55397-w
UR - https://doi.org/10.1038/s41598-026-55397-w
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-55397-w",
"type": "article-journal",
"title": "Fast surface reconstruction of human brain MRI: benchmarking deep-learning based morphometry tools",
"container-title": "Scientific reports",
"author": [
{
"family": "Mello",
"given": "Victor B. B."
},
{
"family": "McKinley",
"given": "Richard"
},
{
"family": "Wiest",
"given": "Roland"
},
{
"family": "Rummel",
"given": "Christian"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "20350",
"DOI": "10.1038/s41598-026-55397-w",
"PMID": "42286078",
"PMCID": "PMC13328385",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-55397-w",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
12
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1002/hbm.70560
Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL-Based Cortical Thickness Estimates.
Journal: Human brain mapping
In common: structural MRI / diffusion, 14 references
[2] doi:10.1002/alz.71649 [code]
Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: Nighres, SimpleITK, ANTs, 8 other tools, structural MRI / diffusion, 2 references
[3] doi:10.1038/s41598-026-56778-x [code]
Chiari malformation type 1 is associated with a smaller fourth ventricle volume - a multi-cohort replication study.
Journal: Scientific reports
In common: PyRadiomics, SimpleITK, ANTs, 6 other tools, structural MRI / diffusion, 4 references
[4] doi:10.3389/fonc.2026.1886395 [code]
Resources are associated with functional outcome and brain morphometry in childhood cancer survivors.
Journal: Frontiers in oncology
In common: PyRadiomics, SimpleITK, ANTs, 6 other tools, structural MRI / diffusion, 3 references
[5] doi:10.1002/advs.76596 [code]
DDSurfer: A Weakly-Supervised Dual-Stream Deep Learning Framework for Cortical Surface Reconstruction From Diffusion MRI.
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany)
In common: SimpleITK, ANTs, FreeSurfer, 5 other tools, methods / tools, structural MRI / diffusion, 5 references
[6] doi:10.3389/frai.2026.1771088 [code]
Few-shot deployment of pretrained MRI transformers in brain imaging tasks.
Journal: Frontiers in artificial intelligence
In common: SimpleITK, scikit-image, NiBabel, 5 other tools, methods / tools, structural MRI / diffusion, 5 references
[7] doi:10.1002/hipo.70124 [code]
Association Between Anterior Hippocampal Gyrification and Episodic Memory Performance in Neurotypical Young Adults.
Journal: Hippocampus
In common: Nighres, SimpleITK, scikit-image, 6 other tools, structural MRI / diffusion, 2 references
[8] doi:10.3390/jimaging12070276 [code]
Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration.
Journal: Journal of imaging
In common: SimpleITK, ANTs, scikit-image, 6 other tools, methods / tools, structural MRI / diffusion, 3 references
[9] doi:10.1371/journal.pcbi.1014555 [code]
Body surface potential driven personalisation of electrophysiological digital twins in hypertrophic cardiomyopathy.
Journal: PLoS computational biology
In common: PyRadiomics, SimpleITK, ANTs, 7 other tools, structural MRI / diffusion
[10] doi:10.1038/s41593-026-02359-0 [code]
The cross-site reproducibility of MRI morphometric phenotypes in psychiatric disorders.
Journal: Nature neuroscience
In common: FreeSurfer, NiBabel, scikit-learn, 3 other tools, structural MRI / diffusion, 6 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.